2. 一个简单的网络 2022-09-03

参考官网教程：
https://pytorch.org/tutorials/beginner/basics/quickstart_tutorial.html

打开文件，并写入如下代码，保持为first.py：

#包含头文件
import torch
from torch import nn   #神经网络相关
from torch.utils.data import DataLoader  #数据载入
from torchvision import datasets              #自带数据集
from torchvision.transforms import ToTensor     #tensor数据转换工具


# Download training data from open datasets.
#训练数据集
training_data = datasets.FashionMNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor(),
)

# Download test data from open datasets.
#测试数据集
test_data = datasets.FashionMNIST(
    root="data",
    train=False,
    download=True,
    transform=ToTensor(),
)

batch_size = 64

# Create data loaders.
train_dataloader = DataLoader(training_data, batch_size=batch_size)
test_dataloader = DataLoader(test_data, batch_size=batch_size)

for X, y in test_dataloader:
    print(f"Shape of X [N, C, H, W]: {X.shape}")
    print(f"Shape of y: {y.shape} {y.dtype}")
    break

# Get cpu or gpu device for training.
device = "cuda" if torch.cuda.is_available() else "cpu"    #判断是否使用gpu
print(f"Using {device} device")

# Define model
class NeuralNetwork(nn.Module):
    def __init__(self):
        super(NeuralNetwork, self).__init__()
        self.flatten = nn.Flatten()   #展开成1维向量
        self.linear_relu_stack = nn.Sequential(     #串联网络的定义
            nn.Linear(28*28, 512),  #线性层
            nn.ReLU(),                        #非线性层
            nn.Linear(512, 512),
            nn.ReLU(),
            nn.Linear(512, 10)
        )

    def forward(self, x):       #正向估计函数
        x = self.flatten(x)        #数据展开
        logits = self.linear_relu_stack(x)      #网络计算
        return logits

model = NeuralNetwork().to(device)
print(model)          #强大的print 函数显示模型细节

loss_fn = nn.CrossEntropyLoss()            #损失函数
optimizer = torch.optim.SGD(model.parameters(), lr=1e-3)    #梯度函数

def train(dataloader, model, loss_fn, optimizer):   #模型训练
    size = len(dataloader.dataset)
    model.train()
    for batch, (X, y) in enumerate(dataloader):
        X, y = X.to(device), y.to(device)    #载入GPU 或CPU

        # Compute prediction error
        pred = model(X)                #正向计算
        loss = loss_fn(pred, y)     #计算cost

        # Backpropagation
        optimizer.zero_grad()        #计算梯度
        loss.backward()                  #计算梯度
        optimizer.step()                 #真正训练

        if batch % 100 == 0:
            loss, current = loss.item(), batch * len(X)
            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")

def test(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    model.eval()
    test_loss, correct = 0, 0
    with torch.no_grad():
        for X, y in dataloader:
            X, y = X.to(device), y.to(device)
            pred = model(X)
            test_loss += loss_fn(pred, y).item()
            correct += (pred.argmax(1) == y).type(torch.float).sum().item()
    test_loss /= num_batches
    correct /= size
    print(f"Test Error: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \n")


epochs = 5
for t in range(epochs):
    print(f"Epoch {t+1}\n-------------------------------")
    train(train_dataloader, model, loss_fn, optimizer)
    test(test_dataloader, model, loss_fn)
print("Done!")

torch.save(model.state_dict(), "model.pth")
print("Saved PyTorch Model State to model.pth")

model = NeuralNetwork()
model.load_state_dict(torch.load("model.pth"))


classes = [
    "T-shirt/top",
    "Trouser",
    "Pullover",
    "Dress",
    "Coat",
    "Sandal",
    "Shirt",
    "Sneaker",
    "Bag",
    "Ankle boot",
]

model.eval()
x, y = test_data[0][0], test_data[0][1]
with torch.no_grad():
    pred = model(x)
    predicted, actual = classes[pred[0].argmax(0)], classes[y]
    print(f'Predicted: "{predicted}", Actual: "{actual}"')
    

运行：

python3 first.py

显示如下表示运行成功。

Test Error:
Accuracy: 64.6%, Avg loss: 1.073880

Done!
Saved PyTorch Model State to model.pth
Predicted: "Ankle boot", Actual: "Ankle boot"